skills.rest
mt-krainski
mt-krainskiCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, modify, evaluate, and optimize AI skills with SKILL.md metadata.

1|Updated Oct 3, 2023
Search Tags:#skill development#testing#prompt engineering#optimization#evaluation#ai agent
One-click install
npx skills add https://github.com/mt-krainski/twinkletaps --skill skill-creator-mt-krainski
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/mt-krainski/twinkletaps/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/mt-krainski/twinkletaps --skill skill-creator-mt-krainski

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill empowers users to create new AI capabilities (skills), improve existing ones, and rigorously test their performance, ensuring they are effective and reliable.

Core Features & Use Cases

  • Skill Creation: Guide users through defining intent, writing SKILL.md, and structuring skill resources.
  • Iterative Improvement: Facilitate testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Description Optimization: Automatically tune skill descriptions for optimal triggering accuracy.
  • Use Case: A developer wants to build a new skill that summarizes code files. This Skill will guide them from initial concept to a fully tested and optimized skill, including creating test cases and analyzing results.

Quick Start

Use the skill-creator to help me build a new skill that can generate commit messages from code changes.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create and test a new AI skill from scratch?▼

To create and test an AI skill, define the skill intent, write the SKILL.md metadata, and develop test cases. The skill-creator facilitates this end-to-end lifecycle by guiding resource structuring and running benchmarks for iterative refinement.

What is the best way to evaluate AI agent skill performance?▼

The best way to evaluate AI agent skill performance is by running benchmarks against developed test cases. This skill integrates with evaluation frameworks to provide performance analysis, enabling iterative improvement based on metrics and user feedback.

Do I need to write test cases manually when developing an AI skill?▼

You do not need to write test cases entirely manually when developing an AI skill. The skill-creator supports users in defining skill intent and developing test cases, facilitating automated evaluation and optimization within its framework.

How does iterative improvement work for prompt engineering and skill optimization?▼

Iterative improvement for prompt engineering works by testing, evaluating, and refining skills based on performance metrics. The skill-creator analyzes benchmark results and user feedback to improve skill descriptions and overall triggering accuracy.

Can I use this to modify existing AI agent skills instead of building new ones?▼

Yes, you can use this to modify existing AI agent skills. The skill-creator facilitates the end-to-end lifecycle of AI skills, including modification, evaluation, and optimization to ensure existing capabilities remain effective and reliable.

Related Skills

Explore More Software Engineering Skills→
ibnuhalimmibnuhalimm

Architect

Gather project context and produce a detailed architecture plan.

Community
Advanced
Syedyasir001Syedyasir001

evaluation

Evaluate agent performance using multi-dimensional rubrics for accuracy and tool efficiency.

Community
Advanced
AidenSbVevoAidenSbVevo
1

skill-creator

Create, evaluate, and optimize custom AI skill units with automated testing.

Community
Advanced
yasuwrldhyperyasuwrldhyper

skill-creator

Create and refine AI skills with SKILL.md metadata and benchmark testing.

Community
Advanced